arXiv Open Access 2022

One-stage Action Detection Transformer

Lijun Li Li'an Zhuo Bang Zhang
Lihat Sumber

Abstrak

In this work, we introduce our solution to the EPIC-KITCHENS-100 2022 Action Detection challenge. One-stage Action Detection Transformer (OADT) is proposed to model the temporal connection of video segments. With the help of OADT, both the category and time boundary can be recognized simultaneously. After ensembling multiple OADT models trained from different features, our model can reach 21.28\% action mAP and ranks the 1st on the test-set of the Action detection challenge.

Topik & Kata Kunci

Penulis (3)

L

Lijun Li

L

Li'an Zhuo

B

Bang Zhang

Format Sitasi

Li, L., Zhuo, L., Zhang, B. (2022). One-stage Action Detection Transformer. https://arxiv.org/abs/2206.10080

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2022
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓